English
Related papers

Related papers: Multi-Layer Transformers Gradient Can be Approxima…

200 papers

In this paper we investigate transformer architectures designed for partially observable online reinforcement learning. The self-attention mechanism in the transformer architecture is capable of capturing long-range dependencies and it is…

Machine Learning · Computer Science 2024-10-16 Subhojeet Pramanik , Esraa Elelimy , Marlos C. Machado , Adam White

Recurrent neural networks are effective models to process sequences. However, they are unable to learn long-term dependencies because of their inherent sequential nature. As a solution, Vaswani et al. introduced the Transformer, a model…

Machine Learning · Computer Science 2023-03-28 Quentin Fournier , Gaétan Marceau Caron , Daniel Aloise

We consider the class of optimization problems arising from computationally intensive L1-regularized M-estimators, where the function or gradient values are very expensive to compute. A particular instance of interest is the L1-regularized…

Machine Learning · Statistics 2015-01-26 Kai Zhong , Ian E. H. Yen , Inderjit S. Dhillon , Pradeep Ravikumar

The increasing complexity of deep learning architectures is resulting in training time requiring weeks or even months. This slow training is due in part to vanishing gradients, in which the gradients used by back-propagation are extremely…

Computer Vision and Pattern Recognition · Computer Science 2015-10-16 Bharat Singh , Soham De , Yangmuzi Zhang , Thomas Goldstein , Gavin Taylor

Adjusting the latency, power, and accuracy of natural language understanding models is a desirable objective of an efficient architecture. This paper proposes an efficient Transformer architecture that adjusts the inference computational…

Computation and Language · Computer Science 2024-09-20 Sajjad Kachuee , Mohammad Sharifkhani

LLM post-training typically propagates task gradients through the full depth of the model. Although this end-to-end structure is simple and general, it couples task adaptation to full-depth activation storage, long-range backward…

Computation and Language · Computer Science 2026-05-11 Hengyu Shi , Tianyang Han , Peizhe Wang , Zhiling Wang , Xu Yang , Junhao Su

Gradient-based meta-learning methods leverage gradient descent to learn the commonalities among various tasks. While previous such methods have been successful in meta-learning tasks, they resort to simple gradient descent during…

Machine Learning · Statistics 2018-06-15 Yoonho Lee , Seungjin Choi

Transformers have emerged as a powerful tool for a broad range of natural language processing tasks. A key component that drives the impressive performance of Transformers is the self-attention mechanism that encodes the influence or…

Computation and Language · Computer Science 2021-04-02 Yunyang Xiong , Zhanpeng Zeng , Rudrasis Chakraborty , Mingxing Tan , Glenn Fung , Yin Li , Vikas Singh

State-of-the-art training algorithms for deep learning models are based on stochastic gradient descent (SGD). Recently, many variations have been explored: perturbing parameters for better accuracy (such as in Extragradient), limiting SGD…

Machine Learning · Computer Science 2022-03-23 Amirkeivan Mohtashami , Martin Jaggi , Sebastian U. Stich

In this paper, we propose that the dot product pairwise matching attention layer, which is widely used in Transformer-based models, is redundant for the model performance. Attention, in its original formulation, has to be seen rather as a…

Computation and Language · Computer Science 2022-06-29 Uladzislau Yorsh , Alexander Kovalenko , Vojtěch Vančura , Daniel Vašata , Pavel Kordík , Tomáš Mikolov

Multilingual models jointly pretrained on multiple languages have achieved remarkable performance on various multilingual downstream tasks. Moreover, models finetuned on a single monolingual downstream task have shown to generalize to…

Computation and Language · Computer Science 2022-03-01 Seanie Lee , Hae Beom Lee , Juho Lee , Sung Ju Hwang

In distributed optimization problems, a technique called gradient coding, which involves replicating data points, has been used to mitigate the effect of straggling machines. Recent work has studied approximate gradient coding, which…

Machine Learning · Statistics 2021-08-09 Margalit Glasgow , Mary Wootters

Transformer encoders contextualize token representations by attending to all other tokens at each layer, leading to quadratic increase in compute effort with the input length. In practice, however, the input text of many NLP tasks can be…

Computation and Language · Computer Science 2023-06-01 Jeremiah Milbauer , Annie Louis , Mohammad Javad Hosseini , Alex Fabrikant , Donald Metzler , Tal Schuster

Adaptive gradient methods like AdaGrad are widely used in optimizing neural networks. Yet, existing convergence guarantees for adaptive gradient methods require either convexity or smoothness, and, in the smooth setting, only guarantee…

Machine Learning · Computer Science 2019-10-22 Xiaoxia Wu , Simon S. Du , Rachel Ward

Transformers, and the attention mechanism in particular, have become ubiquitous in machine learning. Their success in modeling nonlocal, long-range correlations has led to their widespread adoption in natural language processing, computer…

Machine Learning · Computer Science 2025-12-23 Edoardo Calvello , Nikola B. Kovachki , Matthew E. Levine , Andrew M. Stuart

Scaling sequence length has become a critical demand in the era of large language models. However, existing methods struggle with either computational complexity or model expressivity, rendering the maximum sequence length restricted. To…

Computation and Language · Computer Science 2023-07-20 Jiayu Ding , Shuming Ma , Li Dong , Xingxing Zhang , Shaohan Huang , Wenhui Wang , Nanning Zheng , Furu Wei

Self-supervised speech representation models, particularly those leveraging transformer architectures, have demonstrated remarkable performance across various tasks such as speech recognition, speaker identification, and emotion detection.…

Audio and Speech Processing · Electrical Eng. & Systems 2025-01-20 Teresa Dorszewski , Albert Kjøller Jacobsen , Lenka Tětková , Lars Kai Hansen

The training process of neural networks is known to be time-consuming, and having a deep architecture only aggravates the issue. This process consists mostly of matrix operations, among which matrix multiplication is the bottleneck. Several…

Machine Learning · Computer Science 2025-06-17 Sana Ebrahimi , Rishi Advani , Abolfazl Asudeh

We study the convergence properties of gradient descent for training deep linear neural networks, i.e., deep matrix factorizations, by extending a previous analysis for the related gradient flow. We show that under suitable conditions on…

Machine Learning · Computer Science 2021-11-25 Gabin Maxime Nguegnang , Holger Rauhut , Ulrich Terstiege

The transformer model is known to be computationally demanding, and prohibitively costly for long sequences, as the self-attention module uses a quadratic time and space complexity with respect to sequence length. Many researchers have…

Computation and Language · Computer Science 2025-05-19 Ziwei He , Meng Yang , Minwei Feng , Jingcheng Yin , Xinbing Wang , Jingwen Leng , Zhouhan Lin